Security audit

多子代理配置飞书

Security checks for vulnerabilities and agentic risk

Overview

This is a straightforward Feishu multi-account setup guide with credential-handling cautions users should keep in mind.

Before installing, make sure any real Feishu appSecret values are kept out of shared repositories, screenshots, and logs, and rotate them if they are accidentally exposed. The skill otherwise appears to be a manual setup guide rather than executable code.

A.I.G

Vulnerability Patterns

Skill Instruction HijackingAlters the agent's session goals or safety constraints when the skill loads
Agent Memory PoisoningWrites attacker-controlled rules into memory that affect later sessions
Remote Payload Retrieval and ExecutionFetches external code whose behavior can change after review
Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally
Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs

SkillSpector

Vulnerability Patterns

Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep

Findings (2)

Missing User Warnings

Medium

Confidence: 95% confidence
Finding: The skill includes plaintext examples showing `appId` and especially `appSecret` directly inside `openclaw.json` without any warning to use secret management, environment-variable substitution, or to avoid committing credentials to source control. In a configuration skill, this normalizes insecure secret handling and can lead users to store production bot credentials in repos, shared files, logs, or screenshots, enabling unauthorized access to Feishu integrations.

Natural-Language Policy Violations

Medium

Confidence: 89% confidence
Finding: The skill name and description are entirely in Chinese, which imposes a specific language choice in user-facing metadata. There is no indication that users can choose another language or that the skill is intentionally limited to a Chinese-speaking or region-specific context.

Static analysis

No suspicious patterns detected.